The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing ch...The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing challenges for real-time applications.Machine learning has shown promise in fiber nonlinear propagation characterization,but the optimization and design of nonlinear systems remain relatively unexplored,especially under multitarget optimization conditions.In this paper,we propose a method that combines deep reinforcement learning(DRL)and deep neural network(DNN)to achieve fast synchronization optimization of ultrafast pulse nonlinear propagation in optical fibers under multitarget optimization tasks,with applications demonstrated in complex SSFS and SC generation systems in the mid-infrared band.The results indicate that a set of optimization parameters can be obtained in a few seconds,enabling rapid,automated tuning of pulse parameters in pursuit of diverse optimization objectives.This integration of DRL and DNN models holds transformative potential for the real-time optimization of not only fiber lasers but also a wide variety of complex photonic systems,paving the way for intelligent,adaptive optical system design and operation.展开更多
Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods o...Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods often face challenges such as indirect prediction,data sparsity,and data drift,which limit their accuracy and generalizability.This study develops an integrated method that combines a knowledge-driven method to directly compute distribution patterns of lithological components,which are used as a priori knowledge to guide the development of a data-driven method.Coupled Markov chain(CMC)and deep neural networks(DNNs)serve as the knowledge-driven and data-driven components,respectively.Additionally,a dynamic prediction strategy is proposed,where the model is continuously optimized as construction progresses and training samples accumulate,rather than being statically trained on post-construction data,as is common in data-driven methods.Finally,the proposed method is evaluated using a real-world project.The evaluation results show that the integrated method outperforms both individual data-and knowledge-driven methods,demonstrating higher predictive performance,greater stability,and greater robustness to data scarcity and data drift.Furthermore,the dynamic prediction strategy better captures the effects of gradual data accumulation and lithological spatial variability on prediction performance during construction,providing new insights for real-time prediction in practical tunneling applications.展开更多
Water inflow into mountain tunnels exhibits high variability and nonlinear seepage behavior,leading to significant prediction inaccuracies and poor pattern recognition when conventional analytical methods are applied....Water inflow into mountain tunnels exhibits high variability and nonlinear seepage behavior,leading to significant prediction inaccuracies and poor pattern recognition when conventional analytical methods are applied.This study proposes a dynamic water inflow prediction method specifically designed for mountain tunnels.The method is based on groundwater dynamics theory,employing nonDarcian law as the governing equation and deriving analytical solutions applicable to both confined and phreatic aquifer conditions.The method incorporates spatiotemporal variations along the tunnel alignment,enabling both short-term and long-term dynamic predictions of water inflow.The study examines the nonlinear characteristics of the seepage field during tunnel water inrush.The research findings indicate that the predictive results are consistent with the hypothesized two-stage water inflow pattern,with relative errors for key parameters,such as maximum water inflow,normal water inflow,and duration of water inflow,remaining within 10%.The magnitude of water inflow is positively correlated with the permeability coefficient,head height;it is negatively correlated with the axial distance to the tunnel face and the non-Darcian influence coefficient.Both water inflow and water pressure are subject to non-Darcian effects within a defined influence zone extending approximately 1.3 times the tunnel diameter.Comparisons with established predictive methods,numerical simulations,and data from existing tunnel projects confirm the effectiveness of the proposed method.Moreover,the method was successfully applied to a mountain tunnel in the Tibet Plateau region in southwestern China,where it achieved prediction errors within 3%to 8%,demonstrating high reliability.展开更多
Dynamic wake field information is vital for the optimized design and control of wind farms.Combined with sparse measurement data from light detection and ranging(LiDAR),the physics-informed neural network(PINN)framewo...Dynamic wake field information is vital for the optimized design and control of wind farms.Combined with sparse measurement data from light detection and ranging(LiDAR),the physics-informed neural network(PINN)frameworks have recently been employed for forecasting freestream wind and wake fields.However,these PINN frameworks face challenges of low prediction accuracy and long training times.Therefore,this paper constructed a PINN framework for dynamic wake field prediction by integrating two accuracy improvement strategies and a step-by-step training time saving strategy.The results showed that the different performance improvement routes significantly improved the overall performance of the PINN.The accuracy and efficiency of the PINN with spatiotemporal improvement strategies were validated via LiDAR-measured data from a wind farm in Shandong province,China.This paper sheds light on load reduction,efficiency improvement,intelligent operation and maintenance of wind farms.展开更多
Based on the hindcast results of summer rainfall anomalies over China for the period 1981-2000 by the Dynamical Climate Prediction System （IAP-DCP） developed by the Institute of Atmospheric Physics, a correction met...Based on the hindcast results of summer rainfall anomalies over China for the period 1981-2000 by the Dynamical Climate Prediction System （IAP-DCP） developed by the Institute of Atmospheric Physics, a correction method that can account for the dependence of model＇s systematic biases on SST anomalies is proposed. It is shown that this correction method can improve the hindcast skill of the IAP-DCP for summer rainfall anomalies over China, especially in western China and southeast China, which may imply its potential application to real-time seasonal prediction.展开更多
This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time...This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.展开更多
Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit mines.Rational valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly...Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit mines.Rational valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly influences the planning of digging trajectories and energy consumption.Load prediction of ECS mainly consists of two types of methods:physics-based modeling and data-driven methods.The former approach is based on known physical laws,usually,it is necessarily approximations of reality due to incomplete knowledge of certain processes,which introduces bias.The latter captures features/patterns from data in an end-to-end manner without dwelling on domain expertise but requires a large amount of accurately labeled data to achieve generalization,which introduces variance.In addition,some parts of load are non-observable and latent,which cannot be measured from actual system sensing,so they can’t be predicted by data-driven methods.Herein,an innovative hybrid physics-informed deep neural network(HPINN)architecture,which combines physics-based models and data-driven methods to predict dynamic load of ECS,is presented.In the proposed framework,some parts of the theoretical model are incorporated,while capturing the difficult-to-model part by training a highly expressive approximator with data.Prior physics knowledge,such as Lagrangian mechanics and the conservation of energy,is considered extra constraints,and embedded in the overall loss function to enforce model training in a feasible solution space.The satisfactory performance of the proposed framework is verified through both synthetic and actual measurement dataset.展开更多
The sea surface temperature （SST） in the In- dian Ocean affects the regional climate over the Asian continent mostly through a modulation of the monsoon system. It is still difficult to provide an a priori indicatio...The sea surface temperature （SST） in the In- dian Ocean affects the regional climate over the Asian continent mostly through a modulation of the monsoon system. It is still difficult to provide an a priori indication of the seasonal variability over the Indian Ocean. It is widely recognized that the warm and cold events of SST over the tropical Indian Ocean are strongly linked to those of the equatorial eastern Pacific. In this study, a statistical prediction model has been developed to predict the monthly SST over the tropical Indian Ocean. This model is a linear regression model based on the lag relationship between the SST over the tropical Indian Ocean and the Nino3.4 （5°S-5°N, 170°W-120°W） SST Index. The pre- dictor （i.e., Nino3.4 SST Index） has been operationally predicted by a large size ensemble E1 Nifio and the Southern Oscillation （ENSO） forecast system with cou- pled data assimilation （Leefs_CDA）, which achieves a high predictive skill of up to a 24-month lead time for the equatorial eastern Pacific SST. As a result, the prediction skill of the present statistical model over the tropical In- dian Ocean is better than that of persistence prediction for January 1982 through December 2009.展开更多
An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models...An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models, this paper proposes a dynamic prediction model of landslide displacement based on singular spectrum analysis(SSA) and stack long short-term memory(SLSTM) network. The SSA is used to decompose the landslide accumulated displacement time series data into trend term and periodic term displacement subsequences. A cubic polynomial function is used to predict the trend term displacement subsequence, and the SLSTM neural network is used to predict the periodic term displacement subsequence. At the same time, the Bayesian optimization algorithm is used to determine that the SLSTM network input sequence length is 12 and the number of hidden layer nodes is 18. The SLSTM network is updated by adding predicted values to the training set to achieve dynamic displacement prediction. Finally, the accumulated landslide displacement is obtained by superimposing the predicted value of each displacement subsequence. The proposed model was verified on the Xintan landslide in Hubei Province, China. The results show that when predicting the displacement of the periodic term, the SLSTM network has higher prediction accuracy than the support vector machine(SVM) and auto regressive integrated moving average(ARIMA). The mean relative error(MRE) is reduced by 4.099% and 3.548% respectively, while the root mean square error(RMSE) is reduced by 5.830 mm and 3.854 mm respectively. It is concluded that the SLSTM network model can better simulate the dynamic characteristics of landslides.展开更多
In order to study dynamic laws of surface movements over coal mines due to mining activities,a dynamic prediction model of surface movements was established,based on the theory of support vector machines(SVM) and time...In order to study dynamic laws of surface movements over coal mines due to mining activities,a dynamic prediction model of surface movements was established,based on the theory of support vector machines(SVM) and times-series analysis.An engineering application was used to verify the correctness of the model.Measurements from observation stations were analyzed and processed to obtain equal-time interval surface movement data and subjected to tests of stationary,zero means and normality.Then the data were used to train the SVM model.A time series model was established to predict mining subsidence by rational choices of embedding dimensions and SVM parameters.MAPE and WIA were used as indicators to evaluate the accuracy of the model and for generalization performance.In the end,the model was used to predict future surface movements.Data from observation stations in Huaibei coal mining area were used as an example.The results show that the maximum absolute error of subsidence is 9 mm,the maximum relative error 1.5%,the maximum absolute error of displacement 7 mm and the maximum relative error 1.8%.The accuracy and reliability of the model meet the requirements of on-site engineering.The results of the study provide a new approach to investigate the dynamics of surface movements.展开更多
A new mobile multicast scheme called mobility prediction based mobile multicast(MPBMM) was proposed. In MPBMM, when a mobile node (MN) roams among subnets during a multicast session, MN predicts the next subnet, to wh...A new mobile multicast scheme called mobility prediction based mobile multicast(MPBMM) was proposed. In MPBMM, when a mobile node (MN) roams among subnets during a multicast session, MN predicts the next subnet, to which MN will attach, by the information of its position and mobility speed, consequently speeds up the handoff procedure. Simulation results show that the proposed scheme can minimize the loss of multicast packets, reduce the delay of subnet handoff, decrease the frequency of multicast tree reconfiguration, and optimize the delivery path of multicast packets. When MN moves among subnets at different speeds (from 5 to 25 ms), the maximum loss ratio of multicast packets is less than0.2%, the maximum inter-arrival time of multicast packets is 117 ms, so the proposed scheme can meet the QoS requirements of real-time services. In addition, MPBMM can support the mobility of multicast source.展开更多
Recentlythearticle"PerioperativevonWillebrandfactordynamics are associated with liver regeneration and predict outcome afterliver resection" was published in Hepatology[1].Prof.Starlinger et al. aimed to ass...Recentlythearticle"PerioperativevonWillebrandfactordynamics are associated with liver regeneration and predict outcome afterliver resection" was published in Hepatology[1].Prof.Starlinger et al. aimed to assess the association of von Willebrand factor (vWF) levels and clinical outcome in patients with liver cancers post-liverresection(LR).Basedonthemechanismthatplatelets accumulation in the liver may promote liver regeneration after partial LR in mice, they found the vWF-dependent pattern of platelets accumulationduringliverregenerationinpatientsaftersurgery.展开更多
The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier us...The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier usually lacks decision-makingevidence. In this paper, we propose a protein secondary structure prediction method withdynamic self-adaptation combination strategy based on entropy, where the weights areassigned according to the entropy of posterior probabilities outputted by base classifiers.The higher entropy value means a lower weight for the base classifier. The final structureprediction is decided by the weighted combination of posterior probabilities. Extensiveexperiments on CB513 dataset demonstrates that the proposed method outperforms theexisting methods, which can effectively improve the prediction performance.展开更多
Can earthquakes be predicted？ How should people overcome the difficulties encountered in the study of earthquake prediction？ This issue can take inspiration from the experiences of weather forecast. Although weather...Can earthquakes be predicted？ How should people overcome the difficulties encountered in the study of earthquake prediction？ This issue can take inspiration from the experiences of weather forecast. Although weather forecasting took a period of about half a century to advance from empirical to numerical forecast, it has achieved significant success. A consensus has been reached among the Chinese seismological community that earth- quake prediction must also develop from empirical fore- casting to physical prediction. However, it is seldom mentioned that physical prediction is characterized by quantitatively numerical predictions based on physical laws. This article discusses five key components for numerical earthquake prediction and their current status. We conclude that numerical earthquake prediction should now be put on the planning agenda and its roadmap designed, seismic stations should be deployed and observations made according to the needs of numerical prediction, and theoretical research should be carried out.展开更多
An analysis of a large number of cases of 500 hPa height monthly prediction shows that systematic errors exist in the zonal mean components which account for a large portion of the total forecast errors, and such erro...An analysis of a large number of cases of 500 hPa height monthly prediction shows that systematic errors exist in the zonal mean components which account for a large portion of the total forecast errors, and such errors are commonly seen in other prediction models. To overcome the difficulties of the numerical model, the authors attempt a 'hybrid' approach to improving the dynamical extended-range (monthly) prediction. The monthly pentad-mean nonlinear dynamical regional prediction model of the zonal-mean geopotential height (wave number 0) based on a large amount of data is constituted by employing the reconstruction of phase-space theory and the spatio-temporal series predictive method. The dynamical prediction of the numerical model is then combined with that of the nonlinear model, i.e., the pentadmean zonal-mean height produced by the nonlinear model is transformed to its counterpart in the numerical model by nudging during the time integration. The forecast experiment results show that the above hybrid approach not only reduces the systematic error in zonal mean height by the numerical model, but also makes an improvement in the non-axisymmetric components due to the wave-flow interaction.展开更多
A low frequency dynamic environment prediction of spacecraft using dynamic substructu- ring is presented. The dynamic environment could be used to describe the level of the excitation on the spacecraft itself and auxi...A low frequency dynamic environment prediction of spacecraft using dynamic substructu- ring is presented. The dynamic environment could be used to describe the level of the excitation on the spacecraft itself and auxiliary equipment. In addition, the dynamic environment is a criterion for the structural dynamic design as well as the ground verification test. The proposed prediction method could solve two major problems. The first is the time consumption of analyzing the whole spacecraft model due to the huge amount of degrees of freedom, and the second is multi-source for component structural dynamic models from distributive departments. To demonstrate the feasibility and efficien- cy, the proposed prediction method is applied to resolve a launching satellite case, and the results were compared with those obtained by the traditional prediction technology using the finite element method.展开更多
According to the characteristic of the sensor inertia, the dynamic prediction to improve the system dynamic precision is presented in this paper. With the recurrence calculation of time constant of the sensor, the sys...According to the characteristic of the sensor inertia, the dynamic prediction to improve the system dynamic precision is presented in this paper. With the recurrence calculation of time constant of the sensor, the system dynamic precision is greatly improved. The example using this method is given.展开更多
The rapid production dynamic prediction of water-flooding reservoirs based on well location deployment has been the basis of production optimization of water-flooding reservoirs.Considering that the construction of ge...The rapid production dynamic prediction of water-flooding reservoirs based on well location deployment has been the basis of production optimization of water-flooding reservoirs.Considering that the construction of geological models with traditional numerical simulation software is complicated,the computational efficiency of the simulation calculation is often low,and the numerical simulation tools need to be repeated iteratively in the process of model optimization,machine learning methods have been used for fast reservoir simulation.However,traditional artificial neural network(ANN)has large degrees of freedom,slow convergence speed,and complex network model.This paper aims to predict the production performance of water flooding reservoirs based on a deep convolutional generative adversarial network(DC-GAN)model,and establish a dynamic mapping relationship between well location deployment and output oil saturation.The network structure is based on an improved U-Net framework.Through a deep convolutional network and deconvolution network,the features of input well deployment images are extracted,and the stability of the adversarial model is strengthened.The training speed and accuracy of the proxy model are improved,and the oil saturation of water flooding reservoirs is dynamically predicted.The results show that the trained DC-GAN has significant advantages in predicting oil saturation by the well-location employment map.The cosine similarity between the oil saturation map given by the trained DC-GAN and the oil saturation map generated by the numerical simulator is compared.In above,DC-GAN is an effective method to conduct a proxy model to quickly predict the production performance of water flooding reservoirs.展开更多
Multicolor soliton dynamics is essential for understanding the soliton interactions in fiber lasers and their triggered nonlinear effects,such as spectral modulation and the switching of soliton states.When studying c...Multicolor soliton dynamics is essential for understanding the soliton interactions in fiber lasers and their triggered nonlinear effects,such as spectral modulation and the switching of soliton states.When studying complex and unsteady dynamics of multicolor solitons in the passive mode-locked fiber laser,not only traditional numerical methods based on the nonlinear Schr?dinger equation require high computational costs and are inefficient,but also single neural network models struggle to capture key dynamic features,such as phase modulation and energy fluctuations during soliton collisions.By effectively extracting the spatial characteristics of soliton interactions and capturing their pulse and spectral evolution,this paper proposes a dual-channel convolutional-recurrent neural network model.This dual-channel model processes the real and imaginary components of the optical complex field data,and accurately predicts the transient evolutionary characteristics of two-color and three-color solitons in the unsteady state,steady state,and their transition process,while capturing key nonlinear dynamical phenomena such as soliton collisions and energy redistribution.Compared with recurrent neural network,this combined model reduces the normalized root mean square error in predicting the positions of soliton collisions by approximately 39%,demonstrates excellent performance in multidimensional dynamic analysis,and offers new tools and insights for optimizing the design of fiber laser.展开更多
Dynamic recrystallization (DRX) behavior in β phase region for the burn resistant titanium alloy Ti?25V?15Cr?0.2Si was investigated with a compression test in the temperature range of 950?1100 °C and the strain ...Dynamic recrystallization (DRX) behavior in β phase region for the burn resistant titanium alloy Ti?25V?15Cr?0.2Si was investigated with a compression test in the temperature range of 950?1100 °C and the strain rate of 0.001?1 s?1. The results show that deformation mechanism of this alloy in hot deformation is dominated by DRX, and new grains of DRX are evolved by bulging nucleation mechanism as a predominant mechanism. DRX occurs more easily with the decrease of strain rate and the increase of deformation temperature. Grain refinement is achieved due to DRX during the hot deformation at strain rate range of 0.01?0.1 s?1 and temperature range of 950?1050 °C. DRX grain coarsening is observed for the alloy deformed at the higher temperatures of 1100 °C and the lower strain rates of 0.001 s?1. Finally, in order to determine the recrystallized fraction and DRX grain size under different deformation conditions, the prediction models of recrystallization kinetics and recrystallized grain sizes were established.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62575051)the Aeronautical Science Foundation of China(Grant No.2023M038080001)+1 种基金the Equipment Pre-research Joint Fund of the Ministry of Education(Grant No.8091B042228)the Science and Technology Project of Sichuan Province(Grant Nos.2023NSFSC1964 and 203NSFSC0033).
文摘The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing challenges for real-time applications.Machine learning has shown promise in fiber nonlinear propagation characterization,but the optimization and design of nonlinear systems remain relatively unexplored,especially under multitarget optimization conditions.In this paper,we propose a method that combines deep reinforcement learning(DRL)and deep neural network(DNN)to achieve fast synchronization optimization of ultrafast pulse nonlinear propagation in optical fibers under multitarget optimization tasks,with applications demonstrated in complex SSFS and SC generation systems in the mid-infrared band.The results indicate that a set of optimization parameters can be obtained in a few seconds,enabling rapid,automated tuning of pulse parameters in pursuit of diverse optimization objectives.This integration of DRL and DNN models holds transformative potential for the real-time optimization of not only fiber lasers but also a wide variety of complex photonic systems,paving the way for intelligent,adaptive optical system design and operation.
基金supported by the Beijing Natural Science Foundation(Grant No.8252012)the National Natural Science Foundation of China(Grant No.52378475).
文摘Accurate acquisition of the lithological composition of a tunnel face is crucial for efficient tunneling and hazard prevention in large-diameter slurry shield tunnels.While widely applied,current data-driven methods often face challenges such as indirect prediction,data sparsity,and data drift,which limit their accuracy and generalizability.This study develops an integrated method that combines a knowledge-driven method to directly compute distribution patterns of lithological components,which are used as a priori knowledge to guide the development of a data-driven method.Coupled Markov chain(CMC)and deep neural networks(DNNs)serve as the knowledge-driven and data-driven components,respectively.Additionally,a dynamic prediction strategy is proposed,where the model is continuously optimized as construction progresses and training samples accumulate,rather than being statically trained on post-construction data,as is common in data-driven methods.Finally,the proposed method is evaluated using a real-world project.The evaluation results show that the integrated method outperforms both individual data-and knowledge-driven methods,demonstrating higher predictive performance,greater stability,and greater robustness to data scarcity and data drift.Furthermore,the dynamic prediction strategy better captures the effects of gradual data accumulation and lithological spatial variability on prediction performance during construction,providing new insights for real-time prediction in practical tunneling applications.
基金the financial support provided by the Key Laboratory of Urban Underground Engineering of Ministry of Education,Beijing Jiaotong University(Grant Nos.TUL2024-05)。
文摘Water inflow into mountain tunnels exhibits high variability and nonlinear seepage behavior,leading to significant prediction inaccuracies and poor pattern recognition when conventional analytical methods are applied.This study proposes a dynamic water inflow prediction method specifically designed for mountain tunnels.The method is based on groundwater dynamics theory,employing nonDarcian law as the governing equation and deriving analytical solutions applicable to both confined and phreatic aquifer conditions.The method incorporates spatiotemporal variations along the tunnel alignment,enabling both short-term and long-term dynamic predictions of water inflow.The study examines the nonlinear characteristics of the seepage field during tunnel water inrush.The research findings indicate that the predictive results are consistent with the hypothesized two-stage water inflow pattern,with relative errors for key parameters,such as maximum water inflow,normal water inflow,and duration of water inflow,remaining within 10%.The magnitude of water inflow is positively correlated with the permeability coefficient,head height;it is negatively correlated with the axial distance to the tunnel face and the non-Darcian influence coefficient.Both water inflow and water pressure are subject to non-Darcian effects within a defined influence zone extending approximately 1.3 times the tunnel diameter.Comparisons with established predictive methods,numerical simulations,and data from existing tunnel projects confirm the effectiveness of the proposed method.Moreover,the method was successfully applied to a mountain tunnel in the Tibet Plateau region in southwestern China,where it achieved prediction errors within 3%to 8%,demonstrating high reliability.
基金supported by the National Natural Science Foundation of China(Grant Nos.12072105,11932006,and 52308498)the Natural Science Foundation of Jiangsu Province,China(Grant No.BK20220976).
文摘Dynamic wake field information is vital for the optimized design and control of wind farms.Combined with sparse measurement data from light detection and ranging(LiDAR),the physics-informed neural network(PINN)frameworks have recently been employed for forecasting freestream wind and wake fields.However,these PINN frameworks face challenges of low prediction accuracy and long training times.Therefore,this paper constructed a PINN framework for dynamic wake field prediction by integrating two accuracy improvement strategies and a step-by-step training time saving strategy.The results showed that the different performance improvement routes significantly improved the overall performance of the PINN.The accuracy and efficiency of the PINN with spatiotemporal improvement strategies were validated via LiDAR-measured data from a wind farm in Shandong province,China.This paper sheds light on load reduction,efficiency improvement,intelligent operation and maintenance of wind farms.
文摘Based on the hindcast results of summer rainfall anomalies over China for the period 1981-2000 by the Dynamical Climate Prediction System （IAP-DCP） developed by the Institute of Atmospheric Physics, a correction method that can account for the dependence of model＇s systematic biases on SST anomalies is proposed. It is shown that this correction method can improve the hindcast skill of the IAP-DCP for summer rainfall anomalies over China, especially in western China and southeast China, which may imply its potential application to real-time seasonal prediction.
文摘This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.
基金National Natural Science Foundation of China(Grant No.52075068)Shanxi Provincial Science and Technology Major Project(Grant No.20191101014).
文摘Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit mines.Rational valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly influences the planning of digging trajectories and energy consumption.Load prediction of ECS mainly consists of two types of methods:physics-based modeling and data-driven methods.The former approach is based on known physical laws,usually,it is necessarily approximations of reality due to incomplete knowledge of certain processes,which introduces bias.The latter captures features/patterns from data in an end-to-end manner without dwelling on domain expertise but requires a large amount of accurately labeled data to achieve generalization,which introduces variance.In addition,some parts of load are non-observable and latent,which cannot be measured from actual system sensing,so they can’t be predicted by data-driven methods.Herein,an innovative hybrid physics-informed deep neural network(HPINN)architecture,which combines physics-based models and data-driven methods to predict dynamic load of ECS,is presented.In the proposed framework,some parts of the theoretical model are incorporated,while capturing the difficult-to-model part by training a highly expressive approximator with data.Prior physics knowledge,such as Lagrangian mechanics and the conservation of energy,is considered extra constraints,and embedded in the overall loss function to enforce model training in a feasible solution space.The satisfactory performance of the proposed framework is verified through both synthetic and actual measurement dataset.
基金supported by the National Basic Research Program of China (Grant No. 2012CB417404)the National Natural Science Foundation of China (Grant Nos.41075064 and 41176014)
文摘The sea surface temperature （SST） in the In- dian Ocean affects the regional climate over the Asian continent mostly through a modulation of the monsoon system. It is still difficult to provide an a priori indication of the seasonal variability over the Indian Ocean. It is widely recognized that the warm and cold events of SST over the tropical Indian Ocean are strongly linked to those of the equatorial eastern Pacific. In this study, a statistical prediction model has been developed to predict the monthly SST over the tropical Indian Ocean. This model is a linear regression model based on the lag relationship between the SST over the tropical Indian Ocean and the Nino3.4 （5°S-5°N, 170°W-120°W） SST Index. The pre- dictor （i.e., Nino3.4 SST Index） has been operationally predicted by a large size ensemble E1 Nifio and the Southern Oscillation （ENSO） forecast system with cou- pled data assimilation （Leefs_CDA）, which achieves a high predictive skill of up to a 24-month lead time for the equatorial eastern Pacific SST. As a result, the prediction skill of the present statistical model over the tropical In- dian Ocean is better than that of persistence prediction for January 1982 through December 2009.
基金supported by the Natural Science Foundation of Shaanxi Province under Grant 2019JQ206in part by the Science and Technology Department of Shaanxi Province under Grant 2020CGXNG-009in part by the Education Department of Shaanxi Province under Grant 17JK0346。
文摘An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models, this paper proposes a dynamic prediction model of landslide displacement based on singular spectrum analysis(SSA) and stack long short-term memory(SLSTM) network. The SSA is used to decompose the landslide accumulated displacement time series data into trend term and periodic term displacement subsequences. A cubic polynomial function is used to predict the trend term displacement subsequence, and the SLSTM neural network is used to predict the periodic term displacement subsequence. At the same time, the Bayesian optimization algorithm is used to determine that the SLSTM network input sequence length is 12 and the number of hidden layer nodes is 18. The SLSTM network is updated by adding predicted values to the training set to achieve dynamic displacement prediction. Finally, the accumulated landslide displacement is obtained by superimposing the predicted value of each displacement subsequence. The proposed model was verified on the Xintan landslide in Hubei Province, China. The results show that when predicting the displacement of the periodic term, the SLSTM network has higher prediction accuracy than the support vector machine(SVM) and auto regressive integrated moving average(ARIMA). The mean relative error(MRE) is reduced by 4.099% and 3.548% respectively, while the root mean square error(RMSE) is reduced by 5.830 mm and 3.854 mm respectively. It is concluded that the SLSTM network model can better simulate the dynamic characteristics of landslides.
基金supported by the Research and Innovation Program for College and University Graduate Students in Jiangsu Province (No.CX10B-141Z)the National Natural Science Foundation of China (No. 41071273)
文摘In order to study dynamic laws of surface movements over coal mines due to mining activities,a dynamic prediction model of surface movements was established,based on the theory of support vector machines(SVM) and times-series analysis.An engineering application was used to verify the correctness of the model.Measurements from observation stations were analyzed and processed to obtain equal-time interval surface movement data and subjected to tests of stationary,zero means and normality.Then the data were used to train the SVM model.A time series model was established to predict mining subsidence by rational choices of embedding dimensions and SVM parameters.MAPE and WIA were used as indicators to evaluate the accuracy of the model and for generalization performance.In the end,the model was used to predict future surface movements.Data from observation stations in Huaibei coal mining area were used as an example.The results show that the maximum absolute error of subsidence is 9 mm,the maximum relative error 1.5%,the maximum absolute error of displacement 7 mm and the maximum relative error 1.8%.The accuracy and reliability of the model meet the requirements of on-site engineering.The results of the study provide a new approach to investigate the dynamics of surface movements.
基金Project (60573127) supported by the National Natural Science Foundation of ChinaProject (20040533036) supported by the Specialized Research Fund for the Doctoral Program of Higher Education of China+1 种基金Project (05JJ40131) supported by the Natural Science Foundation of Hunan Province, ChinaProject(03C326) supported by the Natural Science Foundation of Education Department of Hunan Province, China
文摘A new mobile multicast scheme called mobility prediction based mobile multicast(MPBMM) was proposed. In MPBMM, when a mobile node (MN) roams among subnets during a multicast session, MN predicts the next subnet, to which MN will attach, by the information of its position and mobility speed, consequently speeds up the handoff procedure. Simulation results show that the proposed scheme can minimize the loss of multicast packets, reduce the delay of subnet handoff, decrease the frequency of multicast tree reconfiguration, and optimize the delivery path of multicast packets. When MN moves among subnets at different speeds (from 5 to 25 ms), the maximum loss ratio of multicast packets is less than0.2%, the maximum inter-arrival time of multicast packets is 117 ms, so the proposed scheme can meet the QoS requirements of real-time services. In addition, MPBMM can support the mobility of multicast source.
基金supported by grants from the National Science and Technology Major Project(2017ZX10203201)the opening foundation of the State Key Laboratory for Diagnosis and Treatmentof Infectious Diseases and Collaborative Innovation Center for Diag-nosis and Treatment of Infectious Diseases,First Affiliated Hospital,Zhejiang University School of Medicine(2015KF04)
文摘Recentlythearticle"PerioperativevonWillebrandfactordynamics are associated with liver regeneration and predict outcome afterliver resection" was published in Hepatology[1].Prof.Starlinger et al. aimed to assess the association of von Willebrand factor (vWF) levels and clinical outcome in patients with liver cancers post-liverresection(LR).Basedonthemechanismthatplatelets accumulation in the liver may promote liver regeneration after partial LR in mice, they found the vWF-dependent pattern of platelets accumulationduringliverregenerationinpatientsaftersurgery.
文摘The algorithm based on combination learning usually is superior to a singleclassification algorithm on the task of protein secondary structure prediction. However,the assignment of the weight of the base classifier usually lacks decision-makingevidence. In this paper, we propose a protein secondary structure prediction method withdynamic self-adaptation combination strategy based on entropy, where the weights areassigned according to the entropy of posterior probabilities outputted by base classifiers.The higher entropy value means a lower weight for the base classifier. The final structureprediction is decided by the weighted combination of posterior probabilities. Extensiveexperiments on CB513 dataset demonstrates that the proposed method outperforms theexisting methods, which can effectively improve the prediction performance.
基金supported by the CAS/CAFEA international partnership Program for creative research teams (No.KZZD-EW-TZ-19)China National Science and Technology Support Program ‘‘Practical Techniques for Earthquake Analysis and Prediction Research’’ 2012BAK19B03-5
文摘Can earthquakes be predicted？ How should people overcome the difficulties encountered in the study of earthquake prediction？ This issue can take inspiration from the experiences of weather forecast. Although weather forecasting took a period of about half a century to advance from empirical to numerical forecast, it has achieved significant success. A consensus has been reached among the Chinese seismological community that earth- quake prediction must also develop from empirical fore- casting to physical prediction. However, it is seldom mentioned that physical prediction is characterized by quantitatively numerical predictions based on physical laws. This article discusses five key components for numerical earthquake prediction and their current status. We conclude that numerical earthquake prediction should now be put on the planning agenda and its roadmap designed, seismic stations should be deployed and observations made according to the needs of numerical prediction, and theoretical research should be carried out.
基金The study was financed by theNational Key Project for Development of Science and Tech-nology(96-908-02),by the National Natural Science Foun-dation of China under Grant No.40175013,and partly bythe Project of the Chinese Academy of Sciences (ZKC)
文摘An analysis of a large number of cases of 500 hPa height monthly prediction shows that systematic errors exist in the zonal mean components which account for a large portion of the total forecast errors, and such errors are commonly seen in other prediction models. To overcome the difficulties of the numerical model, the authors attempt a 'hybrid' approach to improving the dynamical extended-range (monthly) prediction. The monthly pentad-mean nonlinear dynamical regional prediction model of the zonal-mean geopotential height (wave number 0) based on a large amount of data is constituted by employing the reconstruction of phase-space theory and the spatio-temporal series predictive method. The dynamical prediction of the numerical model is then combined with that of the nonlinear model, i.e., the pentadmean zonal-mean height produced by the nonlinear model is transformed to its counterpart in the numerical model by nudging during the time integration. The forecast experiment results show that the above hybrid approach not only reduces the systematic error in zonal mean height by the numerical model, but also makes an improvement in the non-axisymmetric components due to the wave-flow interaction.
基金Supported by the Ministerial Level Foundation(2012021)
文摘A low frequency dynamic environment prediction of spacecraft using dynamic substructu- ring is presented. The dynamic environment could be used to describe the level of the excitation on the spacecraft itself and auxiliary equipment. In addition, the dynamic environment is a criterion for the structural dynamic design as well as the ground verification test. The proposed prediction method could solve two major problems. The first is the time consumption of analyzing the whole spacecraft model due to the huge amount of degrees of freedom, and the second is multi-source for component structural dynamic models from distributive departments. To demonstrate the feasibility and efficien- cy, the proposed prediction method is applied to resolve a launching satellite case, and the results were compared with those obtained by the traditional prediction technology using the finite element method.
文摘According to the characteristic of the sensor inertia, the dynamic prediction to improve the system dynamic precision is presented in this paper. With the recurrence calculation of time constant of the sensor, the system dynamic precision is greatly improved. The example using this method is given.
基金supports from the National Natural Science Foundation of China(No.52104017)the Open Foundation of Cooperative Innovation Center of Unconventional Oil and Gas(Ministry of Education&Hubei Province)(No.UOG2022-14)the open fund of the State Center for Research and Development of Oil Shale Exploitation(33550000-21-ZC0611-0008).
文摘The rapid production dynamic prediction of water-flooding reservoirs based on well location deployment has been the basis of production optimization of water-flooding reservoirs.Considering that the construction of geological models with traditional numerical simulation software is complicated,the computational efficiency of the simulation calculation is often low,and the numerical simulation tools need to be repeated iteratively in the process of model optimization,machine learning methods have been used for fast reservoir simulation.However,traditional artificial neural network(ANN)has large degrees of freedom,slow convergence speed,and complex network model.This paper aims to predict the production performance of water flooding reservoirs based on a deep convolutional generative adversarial network(DC-GAN)model,and establish a dynamic mapping relationship between well location deployment and output oil saturation.The network structure is based on an improved U-Net framework.Through a deep convolutional network and deconvolution network,the features of input well deployment images are extracted,and the stability of the adversarial model is strengthened.The training speed and accuracy of the proxy model are improved,and the oil saturation of water flooding reservoirs is dynamically predicted.The results show that the trained DC-GAN has significant advantages in predicting oil saturation by the well-location employment map.The cosine similarity between the oil saturation map given by the trained DC-GAN and the oil saturation map generated by the numerical simulator is compared.In above,DC-GAN is an effective method to conduct a proxy model to quickly predict the production performance of water flooding reservoirs.
基金supported by the National Natural Science Foundation of China(Grant Nos.12261131495,and 12475008)the Scientific Research and Development Fund of Zhejiang A&F University(Grant No.2021FR0009)。
文摘Multicolor soliton dynamics is essential for understanding the soliton interactions in fiber lasers and their triggered nonlinear effects,such as spectral modulation and the switching of soliton states.When studying complex and unsteady dynamics of multicolor solitons in the passive mode-locked fiber laser,not only traditional numerical methods based on the nonlinear Schr?dinger equation require high computational costs and are inefficient,but also single neural network models struggle to capture key dynamic features,such as phase modulation and energy fluctuations during soliton collisions.By effectively extracting the spatial characteristics of soliton interactions and capturing their pulse and spectral evolution,this paper proposes a dual-channel convolutional-recurrent neural network model.This dual-channel model processes the real and imaginary components of the optical complex field data,and accurately predicts the transient evolutionary characteristics of two-color and three-color solitons in the unsteady state,steady state,and their transition process,while capturing key nonlinear dynamical phenomena such as soliton collisions and energy redistribution.Compared with recurrent neural network,this combined model reduces the normalized root mean square error in predicting the positions of soliton collisions by approximately 39%,demonstrates excellent performance in multidimensional dynamic analysis,and offers new tools and insights for optimizing the design of fiber laser.
基金Projects(51261020,51164030)supported by the National Natural Science Foundation of ChinaProject(GF201401007)supported by the Open Fund of National Defense Key Disciplines Laboratory of Light Alloy Processing Science and Technology,China
文摘Dynamic recrystallization (DRX) behavior in β phase region for the burn resistant titanium alloy Ti?25V?15Cr?0.2Si was investigated with a compression test in the temperature range of 950?1100 °C and the strain rate of 0.001?1 s?1. The results show that deformation mechanism of this alloy in hot deformation is dominated by DRX, and new grains of DRX are evolved by bulging nucleation mechanism as a predominant mechanism. DRX occurs more easily with the decrease of strain rate and the increase of deformation temperature. Grain refinement is achieved due to DRX during the hot deformation at strain rate range of 0.01?0.1 s?1 and temperature range of 950?1050 °C. DRX grain coarsening is observed for the alloy deformed at the higher temperatures of 1100 °C and the lower strain rates of 0.001 s?1. Finally, in order to determine the recrystallized fraction and DRX grain size under different deformation conditions, the prediction models of recrystallization kinetics and recrystallized grain sizes were established.
